I just started using tessract OCR and it works nicely with the UZN file included for the command line "tesseract c:\a.png c:\b -psm 4". There are two problems that I encountered, one is that when I try to crop the image rectangle for words with green background, nothing shows up in the output b.txt. I am not sure if tesseract has a way of converting the background to white background or a better way for the words to show. Another problem is one of the word "BRADY" is read as "amxm" with uzn file "355 1014 78 16 Text", the font is small around 12 so I am not sure if there is a way to improve this. Any suggestion is welcome, thanks for the help!
-- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To post to this group, send email to [email protected]. Visit this group at http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/06036dc2-e627-49c0-b638-6473314df5c3%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
